103 citations · 111 across the 11 of their papers we have counts for
15 papers
Sekai: Incremental Event Memory for Generalized Reasoning Video Segmentation
Zhengtao Liu, Jinrong Xu, Shiu-Hong Kao +2
Online reasoning video segmentation (Online RVS) requires a model to segment query-referred objects as a video streams in, using only the frames observed so far. Existing formulati…
From Reasoning Failures to Composable Video Spatial Intelligence
Pengzhan Sun, Junbin Xiao, Ramanathan Rajaraman +2
Spatial reasoning benchmarks evaluate vision-language models across diverse tasks, but task-level scores do not reveal which underlying capabilities account for success or failure.…
Rethinking Probability-Based Reinforcement Learning From Posterior Concentration
Shiu-Hong Kao, Yubo Zhao, Zhenyu Tian +3
Verifier-free reinforcement learning with probability-based rewards offers a promising way to train LLMs on general reasoning tasks where external verifiers are unavailable. Yet th…
Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift
Pengzhan Sun, Shiu-hong Kao, Shijie Li +4
This paper studies \textbf{thinking--answer consistency} in vision-language models. We focus on Visual Intention Grounding, where a model infers a target object based on a human in…
ReSTI: A Source-Grounded Audit and Repair of STI-Bench
Pengzhan Sun, Ramanathan Rajaraman, Shiu-Hong Kao +2
Spatial--temporal benchmarks are valid only when their questions, source annotations, and answer options identify the same physical quantity. We audit STI-Bench against the officia…
CoT-Seg: Rethinking Segmentation with Chain-of-Thought Reasoning and Self-Correction
Shiu-hong Kao, Chak Ho Huang, Huaiqian Liu +2
Existing works of reasoning segmentation often fall short in complex cases, particularly when addressing complicated queries and out-of-domain images. Inspired by the chain-of-thou…
CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos
Shiu-hong Kao, Yu-Wing Tai, Chi-Keung Tang
Reasoning Video Object Segmentation is a challenging task, aiming at generating a mask sequence from an input video given a complex and implicit text query. While existing works fi…
StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams
Yang LI, Jinglu Wang, Lei Chu +4
The advent of 3D Gaussian Splatting (3DGS) has advanced 3D scene reconstruction and novel view synthesis. With the growing interest of interactive applications that need immediate…
Think Before You Segment: High-Quality Reasoning Segmentation with GPT Chain of Thoughts
Shiu-hong Kao, Yu-Wing Tai, Chi-Keung Tang
Reasoning segmentation is a challenging vision-language task that aims to output the segmentation mask with respect to a complex, implicit, and even non-visual query text. Previous…
Beyond and Free from Diffusion: Invertible Guided Consistency Training
Chia-Hong Hsu, Shiu-hong Kao, Randall Balestriero
Guidance in image generation steers models towards higher-quality or more targeted outputs, typically achieved in Diffusion Models (DMs) via Classifier-free Guidance (CFG). However…
UVRM: A Scalable 3D Reconstruction Model from Unposed Videos
Shiu-hong Kao, Xiao Li, Jinglu Wang +4
Large Reconstruction Models (LRMs) have recently become a popular method for creating 3D foundational models. Training 3D reconstruction models with 2D visual data traditionally re…
StableKD: Breaking Inter-block Optimization Entanglement for Stable Knowledge Distillation
Shiu-hong Kao, Jierun Chen, S. H. Gary Chan
Knowledge distillation (KD) has been recognized as an effective tool to compress and accelerate models. However, current KD approaches generally suffer from an accuracy drop and/or…
InceptionHuman: Controllable Prompt-to-NeRF for Photorealistic 3D Human Generation
Shiu-hong Kao, Xinhang Liu, Yu-Wing Tai +1
This paper presents InceptionHuman, a prompt-to-NeRF framework that allows easy control via a combination of prompts in different modalities (e.g., text, poses, edge, segmentation…
Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction
Xinhang Liu, Jiaben Chen, Shiu-hong Kao +2
Novel view synthesis via Neural Radiance Fields (NeRFs) or 3D Gaussian Splatting (3DGS) typically necessitates dense observations with hundreds of input images to circumvent artifa…
Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
Jierun Chen, Shiu-hong Kao, Hao He +4
To design fast neural networks, many works have been focusing on reducing the number of floating-point operations (FLOPs). We observe that such reduction in FLOPs, however, does no…